Scenario2Vector: scenario description language based embeddings for traffic situations
Scenario2Vector: scenario description language based embeddings for traffic situations
复制标题
DOI：
10.1145/3450267.3450544
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
Aron Harder;Jaspreet Ranjit;Madhur Behl
中科院分区：
文献类型：
--
作者：
Aron Harder;Jaspreet Ranjit;Madhur Behl
衡量自动驾驶进展的一个流行指标是“每次干预的英里数”。这远远不是一个足够的指标，它不允许在两辆自动驾驶汽车（AV）的能力之间进行公平比较。在本文中，我们提出了Scenario 2 Vector-一种基于场景描述语言（SDL）的嵌入交通情况，使我们能够自动搜索类似的交通情况，从大型AV数据集。我们的SDL嵌入将AV所经历的交通情况提取为其规范组件-演员，动作和交通场景。然后，我们可以使用此嵌入来评估向量空间中不同交通情况的相似性。我们还创建了第一个此类数据集，即交通场景相似性（TSS）数据集，其中包含交通场景之间相似性的人类排名注释。使用TSS数据，我们比较了我们的SDL嵌入与基于文本标题的搜索方法，如Sentence 2 Vector。我们发现Scenario 2 Vector的性能比Sentence 2 Vector高出13%，这是通过检查它们在类似交通情况下的表现来实现AV之间公平比较的有希望的一步。我们希望Scenario 2 Vector能够对AV社区产生类似于Word 2 Vec/Sent 2 Vec在自然语言处理数据集中所产生的影响。
A popular metric for measuring progress in autonomous driving has been the "miles per intervention". This is nowhere near a sufficient metric and it does not allow for a fair comparison between the capabilities of two autonomous vehicles (AVs). In this paper we propose Scenario2Vector - a Scenario Description Language (SDL) based embedding for traffic situations that allows us to automatically search for similar traffic situations from large AV data-sets. Our SDL embedding distills a traffic situation experienced by an AV into its canonical components - actors, actions, and the traffic scene. We can then use this embedding to evaluate similarity of different traffic situations in vector space. We have also created a first of its kind, Traffic Scenario Similarity (TSS) dataset which contains human ranking annotations for the similarity between traffic scenarios. Using the TSS data, we compare our SDL embedding -with textual caption based search methods such as Sentence2Vector. We find that Scenario2Vector outperforms Sentence2Vector by 13% ; and is a promising step towards enabling fair comparisons among AVs by inspecting how they perform in similar traffic situations. We hope that Scenario2Vector can have a similar impact to the AV community that Word2Vec/Sent2Vec have had in Natural Language Processing datasets.